Goal-conditioned Reinforcement Learning on AntMaze Stitch Large
88Success RateEik-HiQRL
Evaluation Results
| Method | Links | |
|---|---|---|
| Eik-HiQRL2025.12 | 88 | |
| Eik-HIQL2025.12 | 84 | |
| HIQL2025.12 | 74 | |
| TD-SRAction-conditioning=true2025.06 | 29 | |
| BYOL-γAction-conditioning=true2025.06 | 26 | |
| BYOLAction-conditioning=false2025.06 | 26 | |
| QRL2025.12 | 24 | |
| GCBCAction-conditioning=false2025.06 | 24 | |
| TD-SRAction-conditioning=true2025.06 | 23 | |
| BYOL-γAction-conditioning=true2025.06 | 19 | |
| GCIVLAction-conditioning=false2025.06 | 18 | |
| QRLAction-conditioning=false2025.06 | 18 | |
| BYOLAction-conditioning=false2025.06 | 17 | |
| TRAAction-conditioning=false2025.06 | 17 | |
| CRL2025.12 | 13 | |
| TRAAction-conditioning=false2025.06 | 11 | |
| CRLAction-conditioning=false2025.06 | 11 | |
| CRLAction-conditioning=false2025.06 | 11 | |
| GCIQLAction-conditioning=false2025.06 | 7 | |
| GCBCAction-conditioning=false2025.06 | 3 | |
| GCIVLAction-conditioning=false2025.06 | 1 | |
| QRLAction-conditioning=false2025.06 | 1 | |
| GCIQLAction-conditioning=false2025.06 | 0 |